best-tool
Skill0 starsChanged 5 months agoMITView on GitHub
Use when starting any non-trivial task to pick the BEST available capability (skill, plugin, MCP connector, agent, workflow) instead of the first one that works. Maps relevant skills/MCPs/agents, compares, picks the highest-quality fit, announces it, then executes. Trigger with /best-tool or whenever about to start a task by hand without checking for a better tool.
In this repositoryOne other file it gives its agents.
- godmodeSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run this BEFORE executing a non-trivial task, so you use the highest-quality capability available instead of the first one that happens to …
- Distinctive: line 11
Start of any non-trivial task (research, design, build, data pull, doc, scrape, PDF, deploy, review).
- Distinctive: line 27
Do not work by hand when a better tool exists.
- Distinctive: line 29
If nothing fits, say so, then proceed by hand.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
best-tool: pick the best capability, not the first
Run this BEFORE executing a non-trivial task, so you use the highest-quality capability available instead of the first one that happens to work.
When to run
- Start of any non-trivial task (research, design, build, data pull, doc, scrape, PDF, deploy, review).
- Whenever about to do something by hand and unsure a dedicated skill/MCP exists.
- Skip for trivial turns (chat, one-line answer, obvious single-file edit).
Steps
- Name the objective in one line and the task type (code, research, design, data, content, ops, review).
- Map candidates across all layers:
- Skills (Skill tool): scan the available-skills list for a domain match.
- MCP connectors (ToolSearch): search by keyword; include deferred tools (they need ToolSearch before they can be called).
- Agents (Agent tool) and Workflow: for fan-out, parallel, or multi-step work.
- Compare on fit and quality, not convenience. A dedicated skill/MCP beats doing it by hand almost always.
- Pick the best. If two tie, prefer the one more specific to the domain.
- Announce: state which skill/tool/agent you chose and why, in one line.
- Execute with it.
Rule of thumb
- Do not work by hand when a better tool exists.
- First-that-works is a smell. The win is total quality, not speed.
- If nothing fits, say so, then proceed by hand. That is a valid outcome, just make it a decision and not a default.
Related
- For max-capability mode across a whole session (best-tool plus exhaustive plus verify plus persist), see the godmode skill, or say
godmode.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.